CtrlK
BlogDocsLog inGet started
Tessl Logo

miloco-miot-pet-register

宠物成员注册主流程。**用户表达「登记/记住/让系统认识我家的猫/狗等宠物」意图就触发本 SKILL,不要求出现"注册/登记"字面词**——两条通路:①**描述它的样子**(纯文字,如"胖胖是我家橘猫,尾部有白毛、体型偏胖")→ 建花名册 + 写外观;②**发照片/视频** → 观察出多姿态候选参考图 + 共性外观 → 确认 → 落库(花名册 + 识别参照 + 外观)。也覆盖给存量宠物"补充素材"。**只用用户主动提供的信息**(文字或素材):宠物没有"陌生宠物池",不从摄像头挑、不模拟。纯改名 / 删宠物走 miloco-cli pet CRUD。

76

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with complete executable CLI, a clearly sequenced 5-step workflow with mandatory confirmation checkpoints, and well-structured one-level-deep references. Its only weakness is mild repetition of the confirmation/term-blacklist constraints across multiple sections.

Suggestions

Consolidate the repeated 🚨 confirmation/separation constraints (observe↔落库两轮, message只发图+文字话术分开, 禁抽帧/禁拆调) so each is stated once in 关键约束 and merely cross-referenced elsewhere to save tokens.

The 术语黑名单 table and refs_inconsistent handling each appear in several places; consider a single authoritative section with brief pointers to reduce redundancy.

Section 5.5's three branches restate the full two-round observe→confirm flow inline; a compact step reference plus per-branch delta would tighten it without losing actionability.

DimensionReasoningScore

Conciseness

Mostly lean and dense with executable CLI, assuming Claude's competence, but the 🚨 confirmation/separation constraints are restated in multiple places (第三步硬约束, 关键约束, 边界, 异常处理), which could be tightened; it is noticeably above the midpoint rather than fully trimmed.

4 / 5

Actionability

Provides fully executable, copy-paste-ready commands with exact flags and path formats (pet observe --images/--video --save-crops, reference-crops --scores --mode replace/append, profile-write --ops-file with concrete JSON ops), plus return-field semantics and montage/avatar handling covering the common cases.

5 / 5

Workflow Clarity

A clear 5-step pipeline with an explicit user-confirmation validation checkpoint separating observe from 落库, plus feedback loops for 409 collisions (→5.5 three-way branch), detected=false, and species_mismatch/refs_inconsistent—matching the validate→fix→retry pattern for batch/destructive-style operations.

5 / 5

Progressive Disclosure

The body is a well-organized overview with two real, one-level-deep references clearly signaled via markdown links—[references/species-name-parsing.md] for parsing rules and [references/examples.md] for end-to-end scenarios and counter-examples—both verified to exist as files, with content appropriately split.

5 / 5

Total

19

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, comprehensive, and explicitly distinguishes this skill from related CRUD/home-profile skills while providing clear natural-language triggers. It is dense and well-targeted, with no vague fluff.

DimensionReasoningScore

Specificity

Names multiple concrete actions across two pathways—建花名册, 写外观, observe 出多姿态候选参考图 + 共性外观, 落库 (花名册 + 识别参照 + 外观), and补充素材—giving comprehensive coverage of the registration capability.

5 / 5

Completeness

Explicitly answers both what (两条通路 ①描述样子→花名册+外观, ②发照片/视频→observe+共性外观→确认→落库) and when (用户表达...意图就触发本 SKILL) with concrete trigger phrases.

5 / 5

Trigger Term Quality

Covers natural user phrases like 「登记/记住/让系统认识我家的猫/狗等宠物」「发照片/视频」「描述它的样子」「给存量宠物补充素材」 and explicitly notes the literal term 注册/登记 is not required, spanning synonyms and phrasings users actually say.

5 / 5

Distinctiveness Conflict Risk

Clear niche—pet identity registration via 花名册+识别参照+外观—with explicit boundaries excluding pure rename/delete CRUD (→ miloco-cli pet) and the no-陌生池/no-camera distinction, minimizing wrong-skill triggering.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_field

'metadata' should map string keys to string values

Warning

Total

15

/

16

Passed

Repository
XiaoMi/xiaomi-miloco
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.